github-release
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's git history and source code, which could be used to influence the agent's behavior through embedded instructions.
- Ingestion points: In
SKILL.md, the workflow reads output fromgit log(Step 3b),git diff(Step 3a), and the existingCHANGELOG.md(Step 6). - Boundary markers: The skill does not implement delimiters or explicit instructions for the agent to ignore potentially malicious content embedded within commit messages or code comments.
- Capability inventory: The skill has the capability to write to the file system (Step 6), execute
git commitandgit push(Step 7), and create pull requests using theghCLI (Step 8). - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the git history before it is used to populate changelogs and pull request bodies.
Audit Metadata